COCOSDA Workshop 2003 - Sunday 31st August 2003 - 14:00-18:00
Geneva, Switzerland

In conjunction with EuroSpeech2003

Geneva International Conference Centre / Centre International de Conférence de Genève (CICG)
15, rue Varembé, 1202 Geneva, Switzerland

Name First name Organisation
Khalid Choukri ELRA/ELDA
Mohsen Rashwan RDI & Cairo Univ., Egypt
Yong-Ju Lee SITGC Wonkwang Univ. Korea
Shuichi Itahashi University of Tsukuba, Japan
Dijana Petrovska University of Fribourg, Switzerland
Gerard Chollet CNRS-LTCI, GET-ENST, France
Adrian Fourcin University College London, UK
Evelyn Abberton University College London, UK
Christopher Cieri LDC - Univ. of Pennsylvania, USA
Alvin Martin NIST
Djamel Mostefa ELRA/ELDA, France
Mike Maxwell LDC - Univ. of Pennsylvania, USA
Lex Olorenshaw Sony USA
Mike Emonts Sony USA
  Hasegawa-Johason University of Illinois, USA
Astrid Hagen INESC - ID, Portugal
Chafic Mokhel University of Balamand, Lebanon
Akira Kunematsu Univ. of Electro - Communications
Louis Pols Inst Phonetic Sciences, Univ Amsterdam, Netherlands
Odel Monzon Phonetic Systems
Antonio Bonafonte UPC, Spain
Donata Iskra STEX, Netherlands
Justus Roux Univ. Stellenbosh, South Africa
Dafydd Gibbon
Shigeyoshi Kitazawa Shizuoka University
Rob Van Son IFA / ACLC, Univ. Amsterdam, Netherlands

Welcome and General Introduction to the Workshop and COCOSDA
  Khalid Choukri,
Cocosda Convenor and ELRA/ELDA, France
Recent Activities in South Africa
  Professor JC Roux,
University of Stellenbosch, Stellenbosch, South Africa
Recent Activities of Oriental COCOSDA
  Professor Shuichi ITAHASHI,
Institute of Information Sciences and Electronics, University of Tsukuba, Japan
Recent Activities in China (the current available and future agenda of language resources)
  Prof. Bo Xu,
Deputy President of CASIA, Institute of Automation, Chinese Academy of Sciences
An Overview of speech corpus related activities in Korea.
  Professor Yong-Ju Lee,
Wonkwang University, Korea
Recent Activities in Europe and in the Mediterranean Area
  Khalid Choukri,
Recent Activities in North America
  Christopher Cieri,
Linguistic Data Consortium, Philadelphia, PA, USA
Developments and trends in speech technologies for local languages
  Dafydd Gibbon,
Fakultät für Linguistik und Literaturwissenschaft, Universität Bielefeld, Bielefeld, Germany
"Biometric databases and Evaluation".
  Dijana Petrovska et al.
on behalf of the Biomet project
DIUF - Département d'Informatique, Université de Fribourg, Switzerland
General Discussion: COCOSDA mission, Partnership with other organizations (e.g. the new "cocosda for written resources", New initiatives (India), etc.
  All and Roger Tucker, Director, Outside Echo Ltd. For the new initiative in India
For the "Recent Activities in Oceania", a URL will be give with the updates of such activities Professor J Bruce Millar Research School of Information Sciences and Engineering, Australian National University, Canberra, AUSTRALIA


"Overview of Speech Corpora for European Portuguese"
  Astrid Hagen (contact)
  1. Identification of existing speech resources (BDFALA, BD-PUBLICO, SPEECHDAT, ALERT, ...)
  2. Presentation of the major speech corpora regarding:
    1.   Partners    
    2. (Eagles) Typology: Linguistic contents, speaker characteristics, data collection, annotation    
    3. Research efforts
  3. Recent speech recognition results on Portuguese SpeechDat    
    1. Using the SpeechDat reference recognizer    
    2. Using an HMM/MLP hybrid recognizer
Report on the activities on Japanese prosodic corpus
  Professor Shigeyoshi Kitazawa,
Shizuoka University, Shizuoka, Japan
Validation and Quality of Spoken Language Resources: Orientel - Collection of Speech Ressources for the Mediterranean and Middle East Countries.
  Dr Dorota J. Iskra,
SPEX, Erasmusplein 1, 6525 HT Nijmegen, the Netherlands
Speech to Speech Translation - to be confirmed
  Asuncion Moreno And Antonio Bonafonte,
TALP Research Center, Departament de Teoria del Senyal i Comunicacions, Universitat Politècnica de Catalunya, Barcelona, Spain
A brand new virtual speech archive: "Datenbank Gesprochenes Deutsch",
  Dr. Peter Wagener,
Institut für Deutsche Sprache, R 5, 6-13, D-68161 Mannheim